Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1337 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2569. Min Range: -5.2569
Max Act: 5.2569. Min Act: -0.1700
Data Index: 233915 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2569. Min Range: -5.2569
Max Act: 5.1631. Min Act: -0.1700
Data Index: 6962454 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2569. Min Range: -5.2569
Max Act: 5.0694. Min Act: -0.1700
Data Index: 5849317 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2569. Min Range: -5.2569
Max Act: 5.0381. Min Act: -0.1700
Data Index: 5795571 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2569. Min Range: -5.2569
Max Act: 5.0069. Min Act: -0.1700
Data Index: 4281607 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.9756. Min Act: -0.1700
Data Index: 3775181 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2569. Min Range: -5.2569
Max Act: 5.0069. Min Act: -0.1700
Data Index: 5437492 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.9756. Min Act: -0.1700
Data Index: 1725288 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.9131. Min Act: -0.1700
Data Index: 2820932 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.9131. Min Act: -0.1700
Data Index: 3865409 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.9131. Min Act: -0.1700
Data Index: 1644208 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.8819. Min Act: -0.1700
Data Index: 368860 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.8819. Min Act: -0.1700
Data Index: 6572578 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.8506. Min Act: -0.1700
Data Index: 4796013 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.8194. Min Act: -0.1700
Data Index: 4072711 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.8194. Min Act: -0.1700
Data Index: 7384189 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.8194. Min Act: -0.1700
Data Index: 5737334 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.8194. Min Act: -0.1700
Data Index: 1221395 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.8194. Min Act: -0.1700
Data Index: 7607953 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2569. Min Range: -5.2569
Max Act: 4.7881. Min Act: -0.1700
Data Index: 4301960 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19